Systems and Methods for Determining Price Bands and User Price Affinity Predictions Using Machine Learning Architectures and Techniques

2. The system of claim 1, wherein the one or more price affinity predictions are utilized to predict whether the user will purchase an item from one or more of the price bands.

3. The system of claim 1, wherein each of the price brands are associated with a respective price range boundary for a respective item of the items included in the item type category.

4. The system of claim 1, wherein the affinity prediction model utilizes at least one of the following to generate the one or more price affinity predictions: a multi-class logistic regression model or a decision tree model.

5. The system of claim 1, wherein the machine learning architecture further comprises a similarity model that is configured to generate item-item price similarity scores indicating a similarity between a pair of items included in separate item type categories, and the item-item price similarity scores are generated based, at least in part, on the price bands associated with each of the pair of items.

6. The system of claim 5, wherein the similarity model utilizes a matrix factorization model to generate the item-item price similarity scores.

7. The system of claim 5, wherein the similarity model utilizes a Pearson correlation model to generate the item-item price similarity scores.

8. The system of claim 1, wherein the machine learning architecture further comprises a ranking engine that is configured to generate ranking results, and the ranking results are generated based, at least in part, on the one or more price affinity predictions.

9. The system of claim 8, wherein the ranking engine further utilizes item-item price similarity scores to generate the ranking results.

10. The system of claim 8, wherein the one or more price affinity predictions for the user are utilized by one or more end-user applications to personalize or customize one or more outputs on an electronic platform, and the one or more outputs comprise one or more of: a recommendation result for one or more recommended items of the items, a search result of one or more sought items of the items, or an advertisement for one or more advertisements of the items.

12. The method of claim 11, wherein the one or more price affinity predictions are utilized to predict whether the user will purchase an item from one or more of the price bands.

13. The method of claim 11, wherein each of the price brands are associated with a respective price range boundary for a respective item of the items included in the item type category.

14. The method of claim 11, wherein the affinity prediction model utilizes at least one of the following to generate the one or more price affinity predictions: a multi-class logistic regression model or a decision tree model.

15. The method of claim 11, wherein the machine learning architecture further comprises a similarity model that is configured to generate item-item price similarity scores indicating a similarity between a pair of items included in separate item type categories, and the item-item price similarity scores are generated based, at least in part, on the price bands associated with each of the pair of items.

16. The method of claim 15, wherein the similarity model utilizes a matrix factorization model to generate the item-item price similarity scores.

17. The method of claim 15, wherein the similarity model utilizes a Pearson correlation model to generate the item-item price similarity scores.

18. The method of claim 11, wherein the machine learning architecture further comprises a ranking engine that is configured to generate ranking results, and the ranking results are generated based, at least in part, on the one or more price affinity predictions.

19. The method of claim 18, wherein the ranking engine further utilizes item-item price similarity scores to generate the ranking results.

20. The method of claim 18, wherein the one or more price affinity predictions for the user are utilized by one or more end-user applications to personalize or customize one or more outputs on an electronic platform, and the one or more outputs comprise one or more of: a recommendation result for one or more recommended items of the items, a search result of one or more sought items of the items, or an advertisement for one or more advertisements of the items.